# packages
library(metaDigitise)
library(magrittr)
library(tibble)
library(dplyr)
library(lubridate)
library(dpeatdecomposition)
library(dm)
library(RMariaDB)Connect to database
# connect to database
con <-
RMariaDB::dbConnect(
drv = RMariaDB::MariaDB(),
dbname = "dpeatdecomposition",
default.file = "~/my.cnf"
)
# get database as dm object
dm_dpeatdecomposition <-
dpeatdecomposition::dp_get_dm(con, learn_keys = TRUE)Get most current IDs
id_last <-
list(
id_dataset =
dm_dpeatdecomposition %>%
dm::pull_tbl(datasets) %>%
dplyr::pull(id_dataset) %>%
tail(1),
id_sample =
dm_dpeatdecomposition %>%
dm::pull_tbl(samples) %>%
dplyr::pull(id_sample) %>%
tail(1),
id_measurement =
dm_dpeatdecomposition %>%
dm::pull_tbl(data) %>%
dplyr::pull(id_measurement) %>%
tail(1)
) %>%
purrr::map(function(.x) {
if(length(.x) == 0) {
0L
} else {
.x
}
})Create directories
dir_name <- "d31"
dir_source <- "../raw_data/data/d31"
dir_target <- paste0("../derived_data/", id_last$id_dataset + 1L)
if(!dir.exists(dir_target)) {
dir.create(dir_target)
}datasets <-
tibble::tibble(
id_dataset = id_last$id_dataset + 1L
)citations_to_datasets <-
dplyr::bind_rows(
db_template_tables$citations_to_datasets,
tibble::tibble(
id_dataset = datasets$id_dataset,
id_citation = c("Asada.2005b")
)
)# mass remaining
samples2 <-
readODS::read_ods(paste0(dir_source, "/derived/Asada.2005b-Tab2.ods")) %>%
dplyr::rename(
mass_relative_mass = "mass_loss",
mass_relative_mass_error = "mass_remaining_error",
mass_relative_mass_error_type = "mass_remaining_error_type",
mass_relative_mass_sample_size = "mass_remaining_sample_size",
sample_microhabitat = "microtopography",
comments_samples = "comment_samples"
) %>%
dplyr::mutate(
mass_relative_mass = (100 - mass_relative_mass),
dplyr::across(dplyr::any_of(c("mass_relative_mass", "mass_relative_mass_error")), function(.x) .x/100),
dplyr::across(dplyr::ends_with(c("_longitude", "_latitude")), function(.x) {
.x %>%
sp::char2dms(chd = "°", chm = "'", chs = "''") %>%
as.numeric()
}),
sampling_date = as.Date(paste0(sampling_year, "-", sampling_month, "-", sampling_day)),
incubation_duration =
(sampling_date - as.Date("1998-08-11")) %>%
lubridate::time_length(unit = "days"),
site_label = site_name,
mesh_size_absolute = 0.2,
mass_absolute = NA_real_,
is_incubated = TRUE,
incubation_environment = "peat",
id_dataset = datasets$id_dataset[[1]],
experimental_design =
paste0(
as.numeric(as.factor(site_label)), "_",
as.numeric(as.factor(Asada.2004_community_label))
),
type =
dplyr::case_when(
incubation_duration == 0 ~ "samples2",
TRUE ~ "samples3"
)
) %>%
dplyr::filter(!is.na(Asada.2004_community_label))
# litter collection
samples1 <-
samples2 %>%
dplyr::slice(1) %>%
dplyr::mutate(
id_sample = seq_len(nrow(.)) + id_last$id_sample,
id_sample_origin = id_sample,
id_sample_parent = id_sample,
id_sample_incubation_start = NA_integer_,
sample_treatment = "control",
experimental_design = NA_character_,
is_incubated = FALSE,
incubation_environment = NA_character_,
sample_depth_upper = origin_sampling_depth_upper,
sample_depth_lower = origin_sampling_depth_lower,
sampling_date = as.Date("1998-07-15"),
sampling_year = lubridate::year(sampling_date),
sampling_month = lubridate::month(sampling_date),
sampling_day = NA_real_
)
# add missing ids
samples2 <-
samples2 %>%
dplyr::mutate(
id_sample = seq_len(nrow(.)) + max(samples1$id_sample),
id_sample_origin =
dplyr::left_join(
samples2 %>% dplyr::select(taxon_rank_value),
samples1 %>% dplyr::select(taxon_rank_value, id_sample),
by = c("taxon_rank_value")
) %>%
dplyr::pull(id_sample),
id_sample_incubation_start =
purrr::map_int(seq_len(nrow(.)), function(i) {
index <- paste0(taxon_rank_value, "_", site_label, "_", taxon_organ, "_", sample_depth_upper, "_", sample_depth_lower) == paste0(taxon_rank_value, "_", site_label, "_", taxon_organ, "_", sample_depth_upper, "_", sample_depth_lower)[[i]] & experimental_design == experimental_design[[i]] & incubation_duration == 0.0
id_sample[index]
}),
id_sample_parent =
purrr::map_int(seq_len(nrow(.)), function(i) {
index <- paste0(taxon_rank_value, "_", site_label, "_", taxon_organ, "_", sample_depth_upper, "_", sample_depth_lower) == paste0(taxon_rank_value, "_", site_label, "_", taxon_organ, "_", sample_depth_upper, "_", sample_depth_lower)[[i]] & experimental_design == experimental_design[[i]] & incubation_duration < incubation_duration[[i]]
if(! any(index)) {
id_sample_origin[[i]]
} else {
target_incubation_duration <- max(incubation_duration[index])
index <- index & incubation_duration == target_incubation_duration
id_sample[index]
}
})
)
# litter chemistry
d31_litter_chemistry <-
dplyr::bind_rows(
readRDS(paste0(dir_source, "/raw/caldat/Asada.2005b-Fig3a"))$processed_data %>%
dplyr::mutate(
microcommunity = "Menyanthes trifoliata"
),
readRDS(paste0(dir_source, "/raw/caldat/Asada.2005b-Fig3b"))$processed_data %>%
dplyr::mutate(
microcommunity = "Carex utriculata–Sphagnum lindbergii"
),
readRDS(paste0(dir_source, "/raw/caldat/Asada.2005b-Fig3c"))$processed_data %>%
dplyr::mutate(
microcommunity = "Sphagnum austinii"
),
readRDS(paste0(dir_source, "/raw/caldat/Asada.2005b-Fig3d"))$processed_data %>%
dplyr::mutate(
microcommunity = "Rhynchospora alba–Sphagnum tenellum"
),
readRDS(paste0(dir_source, "/raw/caldat/Asada.2005b-Fig3e"))$processed_data %>%
dplyr::mutate(
microcommunity = "Racomitrium lanuginosum"
)
) %>%
dplyr::select(id, y, x, microcommunity) %>%
dplyr::mutate(
y = y/100,
x = purrr::map_int(x, function(.x) {
which.min(abs(1:2 - .x))
}),
incubation_duration =
dplyr::case_when(
x == 1 ~ 365,
x == 2 ~ 709
),
C_relative_mass2 =
dplyr::case_when(
stringr::str_detect(id, "variableC") ~ y,
TRUE ~ NA_real_
),
N_relative_mass2 =
dplyr::case_when(
stringr::str_detect(id, "variableN") ~ y,
TRUE ~ NA_real_
),
sample_depth_upper =
dplyr::case_when(
stringr::str_detect(id, "depth1") ~ 5,
stringr::str_detect(id, "depth2") ~ 20,
stringr::str_detect(id, "depth3") ~ 40
),
sample_depth_lower =
dplyr::case_when(
stringr::str_detect(id, "depth1") ~ 15,
stringr::str_detect(id, "depth2") ~ 30,
stringr::str_detect(id, "depth3") ~ 50
)
) %>%
dplyr::select(-id, -x)
d31_litter_chemistry <-
d31_litter_chemistry %>%
dplyr::filter(!is.na(C_relative_mass2)) %>%
dplyr::select(-N_relative_mass2) %>%
dplyr::bind_cols(
d31_litter_chemistry %>%
dplyr::filter(!is.na(N_relative_mass2)) %>%
dplyr::select(N_relative_mass2)
)
d31_litter_chemistry <-
dplyr::bind_rows(
d31_litter_chemistry,
d31_litter_chemistry %>%
dplyr::filter(incubation_duration == 365) %>%
dplyr::mutate(
incubation_duration = 0,
C_relative_mass2 = 1,
N_relative_mass2 = 1
)
) %>%
dplyr::mutate(
N_absolute = NA_real_,
C_absolute = NA_real_
) %>%
dplyr::select(-y)
samples2 <-
dplyr::left_join(
samples2,
d31_litter_chemistry,
by = c("microcommunity", "incubation_duration", "sample_depth_upper", "sample_depth_lower")
)
## combine
samples <-
dplyr::bind_rows(
db_template_tables$samples,
samples1 %>%
dplyr::mutate(
type = "samples1"
),
samples2
)samples_to_samples <-
samples %>%
dplyr::filter(! id_sample %in% id_sample_origin) %>%
dplyr::mutate(
transition_description =
dplyr::case_when(
type %in% c("samples2") ~ "translocate",
type %in% c("samples3") ~ "wait",
TRUE ~ NA_character_
)
) %>%
dplyr::select(id_sample_parent, id_sample, transition_description) %>%
dplyr::rename(
id_sample_child = "id_sample"
)d2 <-
samples2 %>%
tidyr::pivot_longer(
cols = dplyr::all_of(c("mass_absolute", "mass_relative_mass", "mesh_size_absolute", "N_relative_mass2", "C_relative_mass2", "C_absolute", "N_absolute")),
names_to = "attribute_name",
values_to = "value"
) %>%
dplyr::mutate(
id_measurement = seq_len(nrow(.)) + id_last$id_measurement,
id_measurement_numerator =
purrr::map_int(seq_len(nrow(.)), function(i) {
switch(
attribute_name[[i]],
"N_relative_mass2" = ,
"C_relative_mass2" = {
id_measurement[id_sample == id_sample[[i]] & attribute_name == stringr::str_replace(attribute_name[[i]], "_relative_mass2?", "_absolute")]
},
"mass_relative_mass" = {
id_measurement[id_sample == id_sample[[i]] & attribute_name == "mass_absolute"]
},
NA_integer_
)
}),
id_measurement_denominator =
purrr::map_int(seq_len(nrow(.)), function(i) {
switch(
attribute_name[[i]],
"C_relative_mass2" = ,
"N_relative_mass2" = {
id_measurement[id_sample == id_sample_incubation_start[[i]] & attribute_name == stringr::str_replace(attribute_name[[i]], "_relative_mass2?", "_absolute")]
},
"mass_relative_mass" = {
id_measurement[id_sample == id_sample_incubation_start[[i]] & attribute_name == "mass_absolute"]
},
NA_integer_
)
}),
value_type =
dplyr::case_when(
attribute_name == "mesh_size_absolute" ~ "point",
TRUE ~ "mean"
)
)
d2_sample_size <-
samples2 %>%
tidyr::pivot_longer(
cols = dplyr::ends_with("_sample_size"),
names_to = "attribute_name",
values_to = "sample_size"
) %>%
dplyr::mutate(
attribute_name =
attribute_name %>%
stringr::str_remove(pattern = "_sample_size$")
) %>%
dplyr::select(id_sample, attribute_name, sample_size)
d2_error <-
samples2 %>%
tidyr::pivot_longer(
cols = dplyr::ends_with(c("_error")),
names_to = "attribute_name",
values_to = "error"
) %>%
dplyr::mutate(
attribute_name =
attribute_name %>%
stringr::str_remove(pattern = "_error$")
) %>%
dplyr::select(id_sample, attribute_name, error)
d2_error_type <-
samples2 %>%
tidyr::pivot_longer(
cols = dplyr::ends_with(c("_error_type")),
names_to = "attribute_name",
values_to = "error_type"
) %>%
dplyr::mutate(
attribute_name =
attribute_name %>%
stringr::str_remove(pattern = "_error_type$")
) %>%
dplyr::select(id_sample, attribute_name, error_type)
d2 <-
d2 %>%
dplyr::mutate(
error =
dplyr::left_join(d2, d2_error, by = c("id_sample", "attribute_name")) %>%
dplyr::pull(error),
error_type =
dplyr::left_join(d2, d2_error_type, by = c("id_sample", "attribute_name")) %>%
dplyr::pull(error_type),
sample_size =
dplyr::left_join(d2, d2_sample_size, by = c("id_sample", "attribute_name")) %>%
dplyr::pull(sample_size)
)
# correct attribute names
d2 <-
d2 %>%
dplyr::mutate(
attribute_name =
dplyr::case_when(
attribute_name %in% c("C_relative_mass2", "N_relative_mass2") ~ stringr::str_remove(attribute_name, "2$"),
TRUE ~ attribute_name
)
)
# combine
d <-
dplyr::bind_rows(
db_template_tables$data,
d2
) %>%
dplyr::select(dplyr::all_of(colnames(db_template_tables$data)))experimental_design_format <-
tibble::tibble(
id_dataset = datasets$id_dataset,
file = paste0(id_last$id_dataset + 1L, "/experimental_design_format.csv"),
experimental_design_description = "`site_name`: Name of the site. `Asada.2004_community_label`: Label for the vegetation community (see the article for details)."
)
# csv file to export
experimental_design_format2 <-
samples %>%
dplyr::filter(! is.na(experimental_design)) %>%
dplyr::filter(! duplicated(experimental_design)) %>%
dplyr::select(experimental_design, site_name, Asada.2004_community_label)
# export
write.csv(experimental_design_format2, paste0(dir_target, "/experimental_design_format.csv"), row.names = FALSE)# list all tables
dm_insert_in <-
list(
datasets =
datasets %>%
dplyr::select(dplyr::all_of(colnames(dm_dpeatdecomposition$datasets))),
samples =
samples %>%
dplyr::select(dplyr::all_of(colnames(dm_dpeatdecomposition$samples))),
data =
d %>%
dplyr::select(dplyr::all_of(colnames(dm_dpeatdecomposition$data))),
samples_to_samples =
samples_to_samples %>%
dplyr::select(dplyr::all_of(colnames(dm_dpeatdecomposition$samples_to_samples))),
citations_to_datasets =
citations_to_datasets %>%
dplyr::select(dplyr::all_of(colnames(dm_dpeatdecomposition$citations_to_datasets))),
experimental_design_format =
experimental_design_format %>%
dplyr::select(dplyr::all_of(colnames(dm_dpeatdecomposition$experimental_design_format)))
)
# check whether all column names as present in table attributes
all_column_names <-
purrr::map(dm_insert_in, colnames) %>%
unlist() %>%
unique()
if(! all(all_column_names %in% (dm_dpeatdecomposition %>% dm::pull_tbl(attributes) %>% dplyr::pull(attribute_name)))) {
cond <- purrr::map_lgl(all_column_names, function(.x) ! .x %in% (dm_dpeatdecomposition %>% dm::pull_tbl(attributes) %>% dplyr::pull(attribute_name)))
RMariaDB::dbDisconnect(con)
stop(paste0("New `attribute_name`s discovered: ", paste(all_column_names[cond], collapse = ", ")))
}
all_data_attributes <- unique(dm_insert_in$data$attribute_name)
if(! all(all_data_attributes %in% (dm_dpeatdecomposition %>% dm::pull_tbl(attributes) %>% dplyr::pull(attribute_name)))) {
RMariaDB::dbDisconnect(con)
cond <- purrr::map_lgl(all_data_attributes, function(.x) ! .x %in% (dm_dpeatdecomposition %>% dm::pull_tbl(attributes) %>% dplyr::pull(attribute_name)))
stop(paste0("New `attribute_name`s discovered: ", paste(all_data_attributes[cond], collapse = ", ")))
}
# filter empty tables
dm_insert_in_check <-
dm_insert_in[purrr::map_lgl(dm_insert_in, function(x) nrow(x) > 0)] %>%
dm::as_dm() %>%
dp_dm_add_keys(dm_dpeatdecomposition)
# copy into dm_pmird
for(i in seq_along(dm_insert_in)) {
RMariaDB::dbAppendTable(con, name = names(dm_insert_in)[[i]], value = dm_insert_in[[i]])
}
RMariaDB::dbDisconnect(con)